Advanced Materials Research Vols. 931-932

Abstract: This paper describes the design, implementation, testing, and evaluation of a Thai handwriting practice application for pre-primary school students, aged 4 to 6 years old, aimed at Android tablets. The application provides mechanisms for alphabet validation, score calculation, and handwriting tutorial animations.

Abstract: This research presents the result of study and development of image processing program to monitor the copper wire placement process prior to the autonomous soldering process. The program has been developed using Visual Studio C++6.0 with Open CV, which is software that is on the command image processing. The experiment has 3 parameters to consider, focal length of camera, color of lighting and lighting control the pieces. The experiment shows the result that control ambient light improve the image processing output. Using focal length of 100 mm gives error of less using focal length of 130 mm. The light illuminated color affects the reflection, red-light gives low reflect, compare to white-light. The image processing using this setup can detect soldering point up to 98.5 % and 92.5 % of copper wire is detected. The setup using white-light cannot detect soldering coordinates, and able to detect copper wire only 42.5%. To control the ambient light, the focal length of 100 mm, and the red illuminating suited for the image processing system of the autonomous soldering and copper wire placement.

Abstract: Since millions of documents are available on the Internet, some documents contain similar content but they are written in different languages by various authors. Unfortunately, the existing search engines do not support to all documents that are relevant to a single language query. Therefore, several researchers have put a huge effort to overcome such a problem. The major problems of a cross language search engine include 1) how to store information in a unify model and represent information of multiple languages documents effectively and 2) how to rank the retrieved multiple language documents and present to a user in the right order. This paper overcomes the first problem using an ontology model and we present a new ranking technique for a cross language information retrieval system (CLIR). Keyword weighting scheme in an ontology and document sections are introduced. Cosine similarity formula is modified to particularly support CLIR. The experimental results show the modified formula obtains more efficient ranking results than the existing method.

Abstract: Processing of a large data set which is known for today as big data processing is still a problem that has not yet a well-defined solution. The data can be both structured and unstructured. For the structured part, eXtensible Markup Language (XML) is a major tool that freely allows document owners to describe and organize their data using their markup tags. One major problem, however, behind this freedom lies in the big data retrieving process. The same or similar information that are described using the different tags or different structures may not be retrieved if the query statements contains different keywords to the one used in the markup tags. The best way to solve this problem is to specify a standard set of the markup tags for each problem domain. The creation of such a standard set if done manually requires a lot of hard work and is a time consuming process. In addition, it may be hard to define terms that are acceptable by all people. This research proposes a model for a new technique, XML Tag Recommendation (XTR) that aims to solve this problem. This technique applies the idea of Case Base Reasoning (CBR) by collecting the most used tags in each domain as a case. These tags come from the collection of related words in WordNet. The WordCount that is the web site to find the frequency of words is applied to choose the most used one. The input (problem) to the XTR system is an XML document contains the tags specified by the document owners. The solution is a set of the recommended tags, which is the most used tags, for the problem domain of the document. Document owners have a freedom to change or not change the tags in their documents and can provide feedback to the XTR system.

Abstract: In this paper we report results of a research aimed at classification Web contents on tourism with a modified Naïve Bayes algorithm. We used Web pages relating touristic information about Thailand. An appropriate light-weight tourism ontology with related terms was used to improve the results, which were categorized into six categories (attractions, accommodation, dining, local product markets, One Tambon One Product (OTOP) shops, and events). The Naïve Bayes algorithm generates results for each category, but Web pages can contain diverse information about tourism spanning over groups. The initial Web classification system could not categorize 130 sites (27.40%) out of 475 tested pages, because those Web pages contain words from more than one category. Therefore, we modified the Naïve Bayes algorithm to improve the efficiency of Web classification, which was then tested with the help of F-Measure: the results show 100% for precision, 97.39% for recall, and 98.58% for F-measure.

Abstract: Good health can be achieved by maintaining good behaviors such as a good night sleep, enough exercise and good nutrition. However, the competitive environment nowadays prevents such good behaviors. Thus, this work aims to develop an application on mobile devices that is able to (1) record the daily sleeping, exercise and nutrition information, (2) analyze the collected information in order to provide a notification or an alarm, and (3) present the analyzed results in a simple and easy to understand format. The proposed application can collect data from other application and from the users. A set of simple data analysis methods is performed on the collected data in order to provide a personal health advice based on the user pre-defined preferences.

Abstract: Most business models of online game companies usually depend on sale of virtual items and the monthly subscription fees. The prediction of player departure could increase revenues by giving special promotions out to the players who are expected to unsubscribe or quit playing the game. This paper proposes a departure prediction approach by using a new feature called SLKdays and a game revisitation. The feature "SLKdays" is defined as "Staytime", which is the time each player spending in an online game, of the last k days, and a game revisitation is the playing frequency in the last month to predict the next month subscription. We explore our new feature "SLKdays" to determine the optimal number of k for the departure prediction. With our proposed feature, the accuracy of the departure prediction is high, 91.92%, and the precision and recall rate are 98.22% and 84.51%.

Abstract: To deal with imbalanced data, this paper proposes a hybrid data balancing technique which incorporates both over and under-sampling approaches. This technique determines how much minority data should be grown as well as how much majority data should be reduced. In this manner, noise introduced to the data due to excessive over-sampling could be avoided. On top of that, the proposed data balancing technique helps to determine the appropriate size of the balanced data and thus computation time required for construction of classifiers would be more efficient. The data balancing technique over samples the minority data through GRSOM method and then under samples the majority data using the bootstrap sampling approach. GRSOM is used in this study because it grows new samples in a non-linear fashion and preserves the original data structure. Performance of the proposed method is tested using four data sets from UCI Machine Learning Repository. Once the data sets are balanced, the committee of classifiers is constructed using these balanced data. The experimental results reveal that our proposed data balancing method provides the best performance.

Abstract: Planning each comprehensive trip is regarded as a complicated and time-consuming task which includes the process starting from searching specific tourist information to planning an itinerary in unfamiliar areas. In response to the decision making challenges that tourists may encounter in planning a trip or discovering a destination, this paper proposes an integrated framework for a system supporting tourists in Thailand. The aim of the framework is to provide a service that considers data from a variety of sources, including static and social data, and then recommends points of interest (POI) and itineraries for POI, based on the requirements and interests of the user. The framework consists of three components: a personalized POI recommendation engine, an itinerary planner, and a mobile application. Together these form the foundation of a personalized travelling information system for Thailand. This paper outlines the basic framework and provides a discussion on the potential issues encountered.

Abstract: This paper introduces an alternative approach of how to build the institutional repository, the multi-platform IR, for research institutes whose internal research units have existing IRs. Firstly, it describes the strategy of IR that harvests data from existing various-platform local repositories, allows researchers to manually input their publication data, provides administrative tool to manipulate the IR database, and includes output interface and search tool for end user. Then the program based on Drupal framework using real data from libraries of Khon Kaen University is provided to demonstrate the investigated strategy. The program perfectly performs all required tasks and could potentially be an example for future IRs of research institutes who would like to consolidate and aggregate existing local IRs.